Continuous Glucose Sensor Signal Processing for Dilution Artifact Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Continuous glucose monitors (CGMs) face inaccuracies due to dilution artifacts caused by the delivery of insulin or other compositions near the sensor, leading to underestimation of true glucose levels, which can result in inappropriate insulin adjustments by patients.
Innovation Solution
A method involving a sensor that measures analyte concentrations in subcutaneous fluid, combines these measurements with forecasting models, such as machine learning or glucoregulatory models, and signal processing to estimate true analyte concentrations, mitigating dilution artifacts by predicting future glucose values and using Kalman filters for optimal estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a composition is delivered near the sensor to enable integrated monitoring and therapy, then device integration and convenience are improved, but measurement precision deteriorates due to dilution artifacts
Solution Approach 1:
The system identifies composition delivery events in advance using pump notifications or flow detection, then preemptively switches to forecasted glucose values before the dilution artifact occurs. This preliminary action prevents the measurement error from affecting the displayed glucose reading.
Solution Approach 2:
A forecast model acts as an intermediary between the sensor and the user interface. Instead of displaying raw sensor measurements directly, the system uses the forecast model to generate compensated glucose values that account for upcoming dilution artifacts, providing accurate readings without the interference.
2Device complexity
If raw sensor measurements are used directly, then device complexity is reduced, but measurement precision deteriorates due to dilution artifacts
Solution Approach 1:
The system continuously monitors sensor readings and compares them with forecast model predictions. When a discrepancy indicating dilution artifact is detected, the system provides feedback by switching to the forecasted values, creating a closed-loop system that automatically corrects measurement errors.
Solution Approach 2:
The system changes the parameter being displayed from raw sensor voltage/current to processed forecasted glucose concentrations. This parameter transformation eliminates the dilution artifact effect while maintaining the essential glucose monitoring function.
3Adaptability or versatility
If the sensor is placed close to the delivery site for integrated device design, then device versatility is improved, but measurement precision deteriorates due to interstitial fluid dilution
Solution Approach 1:
The harmful dilution effect is extracted and identified as a separate detectable event through flow sensors or pump notifications. By taking out the dilution artifact as a distinct phenomenon, the system can compensate for it using forecast models rather than being overwhelmed by the direct measurement error.
Data Source
AI summary
The present disclosure provides methods of measuring of an analyte in a subject to remove a measurement artifact by using a forecasting model to determine the true analyst concentration in a subject. Also herein, the present disclosure provides parameters and models to estimate the true analyte concentration in a subject.